INDEX

Explanations

technical terms and measurements related to sensors and medical monitoring devices

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 road

-0.45

Maz

-0.41

 Sorg

-0.40

рти

-0.39

上演

-0.39

tably

-0.39

Maz

-0.38

 pemuda

-0.38

 Kraft

-0.38

road

-0.38

POSITIVE LOGITS

 sensors

1.26

 sensor

1.11

 Sensors

1.09

sensors

1.03

 sensores

1.01

IntoConstraints

1.00

 Sensor

0.96

 resourceCulture

0.94

 thermocouple

0.93

 probes

0.92

Activations Density 0.637%

technical terms and measurements related to sensors and medical monitoring devices

No Comments

No Known Activations